Llama Guard models
4 Llama Guard models on Hugging Face, from 1.2B to 12.0B parameters. At the precision each one is published in, the smallest needs about 2.8 GB of VRAM (Llama-Phishsense-1B, cheapest live fit: RTX 5060 Ti) and the largest about 26.8 GB (Llama-Guard-4-12B, cheapest live fit: RTX 4080 Super). The cheapest way to run Llama-Phishsense-1B is $0.110/hr.
Llama Guard models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| Llama-Phishsense-1B | 1.2B | BF16 | 2.8 GB | RTX 5060 Ti | $0.110/hr |
| Llama-Guard-3-1B | 1.5B | BF16 | 3.3 GB | RTX 5060 Ti | $0.110/hr |
| Llama-Guard-3-8B | 8.0B | BF16 | 17.9 GB | RTX A5000 | $0.176/hr |
| Llama-Guard-4-12B | 12.0B | BF16 | 26.8 GB | RTX 4080 Super | $0.338/hr |
VRAM is for the precision the model is published in, with the same overhead and an 8,192-token context assumed on every page; see the methodology. The fit shown is the lowest-priced single GPU type that holds the model at that precision, or the lowest-priced multi-GPU set (up to 8) when none does.
